aboutsummaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-12-09 20:55:37 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2014-12-09 20:55:37 -0800
commit5706ffd045c3810912c4982357d7daa721af3464 (patch)
treee238193fc65030fb2287af23b584d772ae9f79e8 /arch
parentc30110608cfba7efff3a5e71914aee7c816115c5 (diff)
parentcfa0bd52d0ba9b852f76c7b3f1055edd5e5c7846 (diff)
Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf events update from Ingo Molnar: "On the kernel side there's few changes, the one that stands out is PEBS machine state sampling support on x86, by Stephane Eranian. On the tooling side: User visible tooling changes: - Don't open the DWARF info multiple times, keeping instead a dwfl handle in struct dso, greatly speeding up 'perf report' on powerpc. (Sukadev Bhattiprolu) - Introduce PARSE_OPT_DISABLED option flag and use it to avoid showing undersired options in tools that provides frontends to 'perf record', like sched, kvm, etc (Namhyung Kim) - Fallback to kallsyms when using the minimal 'ELF' loader (Arnaldo Carvalho de Melo) - Fix annotation with kcore (Adrian Hunter) - Support source line numbers in annotate using a hotkey (Andi Kleen) - Callchain improvements including: * Enable printing the srcline in the history * Make get_srcline fall back to sym+offset (Andi Kleen) - TUI hist_entry browser fixes, including showing missing overhead value for first level callchain. Detected comparing the output of --stdio/--gui (that matched) with --tui, that had this problem. (Namhyung Kim) - Support handling complete branch stacks as histograms (Andi Kleen) Tooling infrastructure changes: - Prep work for supporting per-pkg and snapshot counters in 'perf stat' (Jiri Olsa) - 'perf stat' refactorings, moving stuff from it to evsel.c to use in per-pkg/snapshot format changes (Jiri Olsa) - Add per-pkg format file parsing (Matt Fleming) - Clean up libelf feature support code (Namhyung Kim) - Add gzip decompression support for kernel modules (Namhyung Kim) - More prep patches for Intel PT, including a a thread stack and more stuff made available via the database export mechanism (Adrian Hunter) - More Intel PT work, including a facility to export sample data (comms, threads, symbol names, etc) in a database friendly way, with an script to use this to create a postgresql database. (Adrian Hunter) - Make sure that thread->mg->machine points to the machine where the thread exists (it was being set only for the kmaps kernel modules case, do it as well for the mmaps) and use it to shorten function signatures (Arnaldo Carvalho de Melo) ... and lots of other fixes and smaller improvements" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (91 commits) perf report: In branch stack mode use address history sorting perf report: Add --branch-history option perf callchain: Support handling complete branch stacks as histograms perf stat: Add support for snapshot counters perf stat: Add support for per-pkg counters perf tools: Remove perf_evsel__read interface perf stat: Use read_counter in read_counter_aggr perf stat: Make read_counter work over the thread dimension perf stat: Use perf_evsel__read_cb in read_counter perf tools: Add snapshot format file parsing perf tools: Add per-pkg format file parsing perf evsel: Introduce perf_evsel__read_cb function perf evsel: Introduce perf_counts_values__scale function perf evsel: Introduce perf_evsel__compute_deltas function perf tools: Allow to force redirect pr_debug to stderr. perf tools: Fix segfault due to invalid kernel dso access perf callchain: Make get_srcline fall back to sym+offset perf symbols: Move bfd_demangle stubbing to its only user perf callchain: Enable printing the srcline in the history perf tools: Collapse first level callchain entry if it has sibling ...
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/include/asm/perf_event.h3
-rw-r--r--arch/x86/include/uapi/asm/msr-index.h1
-rw-r--r--arch/x86/kernel/cpu/perf_event.h4
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c15
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c81
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c8
6 files changed, 83 insertions, 29 deletions
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8dfc9fd094a3..dc0f6ed35b08 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -177,6 +177,9 @@ struct x86_pmu_capability {
#define IBS_CAPS_BRNTRGT (1U<<5)
#define IBS_CAPS_OPCNTEXT (1U<<6)
#define IBS_CAPS_RIPINVALIDCHK (1U<<7)
+#define IBS_CAPS_OPBRNFUSE (1U<<8)
+#define IBS_CAPS_FETCHCTLEXTD (1U<<9)
+#define IBS_CAPS_OPDATA4 (1U<<10)
#define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \
| IBS_CAPS_FETCHSAM \
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index e21331ce368f..8f02f6990759 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -206,6 +206,7 @@
#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
#define MSR_AMD64_IBSCTL 0xc001103a
#define MSR_AMD64_IBSBRTARGET 0xc001103b
+#define MSR_AMD64_IBSOPDATA4 0xc001103d
#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
/* Fam 16h MSRs */
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fc5eb390b368..4e6cdb0ddc70 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -253,6 +253,10 @@ struct cpu_hw_events {
#define INTEL_UEVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
+/* Like UEVENT_CONSTRAINT, but match flags too */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \
+ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
#define INTEL_PLD_CONSTRAINT(c, n) \
__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index cbb1be3ed9e4..a61f5c6911da 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -565,6 +565,21 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
perf_ibs->offset_max,
offset + 1);
} while (offset < offset_max);
+ if (event->attr.sample_type & PERF_SAMPLE_RAW) {
+ /*
+ * Read IbsBrTarget and IbsOpData4 separately
+ * depending on their availability.
+ * Can't add to offset_max as they are staggered
+ */
+ if (ibs_caps & IBS_CAPS_BRNTRGT) {
+ rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++);
+ size++;
+ }
+ if (ibs_caps & IBS_CAPS_OPDATA4) {
+ rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++);
+ size++;
+ }
+ }
ibs_data.size = sizeof(u64) * size;
regs = *iregs;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 46211bcc813e..495ae9793628 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -552,18 +552,18 @@ int intel_pmu_drain_bts_buffer(void)
* PEBS
*/
struct event_constraint intel_core2_pebs_event_constraints[] = {
- INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
- INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
- INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
- INTEL_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
- INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
EVENT_CONSTRAINT_END
};
struct event_constraint intel_atom_pebs_event_constraints[] = {
- INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
- INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
- INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
EVENT_CONSTRAINT_END
};
@@ -577,36 +577,36 @@ struct event_constraint intel_slm_pebs_event_constraints[] = {
struct event_constraint intel_nehalem_pebs_event_constraints[] = {
INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
- INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */
INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
- INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
- INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
EVENT_CONSTRAINT_END
};
struct event_constraint intel_westmere_pebs_event_constraints[] = {
INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
- INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
- INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
EVENT_CONSTRAINT_END
};
struct event_constraint intel_snb_pebs_event_constraints[] = {
- INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */
/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
@@ -617,7 +617,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
};
struct event_constraint intel_ivb_pebs_event_constraints[] = {
- INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */
/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
@@ -628,7 +628,7 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
};
struct event_constraint intel_hsw_pebs_event_constraints[] = {
- INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */
/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
@@ -886,6 +886,29 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
regs.bp = pebs->bp;
regs.sp = pebs->sp;
+ if (sample_type & PERF_SAMPLE_REGS_INTR) {
+ regs.ax = pebs->ax;
+ regs.bx = pebs->bx;
+ regs.cx = pebs->cx;
+ regs.dx = pebs->dx;
+ regs.si = pebs->si;
+ regs.di = pebs->di;
+ regs.bp = pebs->bp;
+ regs.sp = pebs->sp;
+
+ regs.flags = pebs->flags;
+#ifndef CONFIG_X86_32
+ regs.r8 = pebs->r8;
+ regs.r9 = pebs->r9;
+ regs.r10 = pebs->r10;
+ regs.r11 = pebs->r11;
+ regs.r12 = pebs->r12;
+ regs.r13 = pebs->r13;
+ regs.r14 = pebs->r14;
+ regs.r15 = pebs->r15;
+#endif
+ }
+
if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
regs.ip = pebs->real_ip;
regs.flags |= PERF_EFLAGS_EXACT;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index f9ed429d6e4f..745b158e9a65 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -449,7 +449,11 @@ static struct attribute *snbep_uncore_qpi_formats_attr[] = {
static struct uncore_event_desc snbep_uncore_imc_events[] = {
INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
{ /* end: all zeroes */ },
};
@@ -2036,7 +2040,11 @@ static struct intel_uncore_type hswep_uncore_ha = {
static struct uncore_event_desc hswep_uncore_imc_events[] = {
INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x00,umask=0x00"),
INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
{ /* end: all zeroes */ },
};

Privacy Policy